1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
|
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
// RUN: %clang_cc1 -triple riscv32 -target-feature +xcvalu -emit-llvm %s -o - \
// RUN: | FileCheck %s
#include <stdint.h>
#include <riscv_corev_alu.h>
// CHECK-LABEL: @test_alu_slet(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[A_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: store i32 [[A:%.*]], ptr [[A_ADDR]], align 4
// CHECK-NEXT: store i32 [[B:%.*]], ptr [[B_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[B_ADDR]], align 4
// CHECK-NEXT: store i32 [[TMP0]], ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: store i32 [[TMP1]], ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: [[TMP4:%.*]] = icmp sle i32 [[TMP2]], [[TMP3]]
// CHECK-NEXT: [[SLE_I:%.*]] = zext i1 [[TMP4]] to i32
// CHECK-NEXT: ret i32 [[SLE_I]]
//
int test_alu_slet(int32_t a, int32_t b) {
return __riscv_cv_alu_slet(a, b);
}
// CHECK-LABEL: @test_alu_sletu(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[A_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: store i32 [[A:%.*]], ptr [[A_ADDR]], align 4
// CHECK-NEXT: store i32 [[B:%.*]], ptr [[B_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[B_ADDR]], align 4
// CHECK-NEXT: store i32 [[TMP0]], ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: store i32 [[TMP1]], ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: [[TMP4:%.*]] = icmp ule i32 [[TMP2]], [[TMP3]]
// CHECK-NEXT: [[SLEU_I:%.*]] = zext i1 [[TMP4]] to i32
// CHECK-NEXT: ret i32 [[SLEU_I]]
//
int test_alu_sletu(uint32_t a, uint32_t b) {
return __riscv_cv_alu_sletu(a, b);
}
// CHECK-LABEL: @test_alu_min(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[A_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: store i32 [[A:%.*]], ptr [[A_ADDR]], align 4
// CHECK-NEXT: store i32 [[B:%.*]], ptr [[B_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[B_ADDR]], align 4
// CHECK-NEXT: store i32 [[TMP0]], ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: store i32 [[TMP1]], ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: [[ELT_MIN_I:%.*]] = call i32 @llvm.smin.i32(i32 [[TMP2]], i32 [[TMP3]])
// CHECK-NEXT: ret i32 [[ELT_MIN_I]]
//
int test_alu_min(int32_t a, int32_t b) {
return __riscv_cv_alu_min(a, b);
}
// CHECK-LABEL: @test_alu_minu(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[A_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: store i32 [[A:%.*]], ptr [[A_ADDR]], align 4
// CHECK-NEXT: store i32 [[B:%.*]], ptr [[B_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[B_ADDR]], align 4
// CHECK-NEXT: store i32 [[TMP0]], ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: store i32 [[TMP1]], ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: [[ELT_MIN_I:%.*]] = call i32 @llvm.umin.i32(i32 [[TMP2]], i32 [[TMP3]])
// CHECK-NEXT: ret i32 [[ELT_MIN_I]]
//
int test_alu_minu(uint32_t a, uint32_t b) {
return __riscv_cv_alu_minu(a, b);
}
// CHECK-LABEL: @test_alu_max(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[A_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: store i32 [[A:%.*]], ptr [[A_ADDR]], align 4
// CHECK-NEXT: store i32 [[B:%.*]], ptr [[B_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[B_ADDR]], align 4
// CHECK-NEXT: store i32 [[TMP0]], ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: store i32 [[TMP1]], ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: [[ELT_MAX_I:%.*]] = call i32 @llvm.smax.i32(i32 [[TMP2]], i32 [[TMP3]])
// CHECK-NEXT: ret i32 [[ELT_MAX_I]]
//
int test_alu_max(int32_t a, int32_t b) {
return __riscv_cv_alu_max(a, b);
}
// CHECK-LABEL: @test_alu_maxu(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[A_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: store i32 [[A:%.*]], ptr [[A_ADDR]], align 4
// CHECK-NEXT: store i32 [[B:%.*]], ptr [[B_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[B_ADDR]], align 4
// CHECK-NEXT: store i32 [[TMP0]], ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: store i32 [[TMP1]], ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: [[ELT_MAX_I:%.*]] = call i32 @llvm.umax.i32(i32 [[TMP2]], i32 [[TMP3]])
// CHECK-NEXT: ret i32 [[ELT_MAX_I]]
//
int test_alu_maxu(uint32_t a, uint32_t b) {
return __riscv_cv_alu_maxu(a, b);
}
// CHECK-LABEL: @test_alu_exths(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[A_ADDR_I:%.*]] = alloca i16, align 2
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca i16, align 2
// CHECK-NEXT: store i16 [[A:%.*]], ptr [[A_ADDR]], align 2
// CHECK-NEXT: [[TMP0:%.*]] = load i16, ptr [[A_ADDR]], align 2
// CHECK-NEXT: store i16 [[TMP0]], ptr [[A_ADDR_I]], align 2
// CHECK-NEXT: [[TMP1:%.*]] = load i16, ptr [[A_ADDR_I]], align 2
// CHECK-NEXT: [[CONV_I:%.*]] = sext i16 [[TMP1]] to i32
// CHECK-NEXT: [[EXTHS_I:%.*]] = sext i16 [[TMP1]] to i32
// CHECK-NEXT: ret i32 [[EXTHS_I]]
//
int test_alu_exths(int16_t a) {
return __riscv_cv_alu_exths(a);
}
// CHECK-LABEL: @test_alu_exthz(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[A_ADDR_I:%.*]] = alloca i16, align 2
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca i16, align 2
// CHECK-NEXT: store i16 [[A:%.*]], ptr [[A_ADDR]], align 2
// CHECK-NEXT: [[TMP0:%.*]] = load i16, ptr [[A_ADDR]], align 2
// CHECK-NEXT: store i16 [[TMP0]], ptr [[A_ADDR_I]], align 2
// CHECK-NEXT: [[TMP1:%.*]] = load i16, ptr [[A_ADDR_I]], align 2
// CHECK-NEXT: [[CONV_I:%.*]] = zext i16 [[TMP1]] to i32
// CHECK-NEXT: [[EXTHZ_I:%.*]] = zext i16 [[TMP1]] to i32
// CHECK-NEXT: ret i32 [[EXTHZ_I]]
//
int test_alu_exthz(uint16_t a) {
return __riscv_cv_alu_exthz(a);
}
// CHECK-LABEL: @test_alu_extbs(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[A_ADDR_I:%.*]] = alloca i8, align 1
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca i8, align 1
// CHECK-NEXT: store i8 [[A:%.*]], ptr [[A_ADDR]], align 1
// CHECK-NEXT: [[TMP0:%.*]] = load i8, ptr [[A_ADDR]], align 1
// CHECK-NEXT: store i8 [[TMP0]], ptr [[A_ADDR_I]], align 1
// CHECK-NEXT: [[TMP1:%.*]] = load i8, ptr [[A_ADDR_I]], align 1
// CHECK-NEXT: [[CONV_I:%.*]] = sext i8 [[TMP1]] to i32
// CHECK-NEXT: [[EXTBS_I:%.*]] = sext i8 [[TMP1]] to i32
// CHECK-NEXT: ret i32 [[EXTBS_I]]
//
int test_alu_extbs(int8_t a) {
return __riscv_cv_alu_extbs(a);
}
// CHECK-LABEL: @test_alu_extbz(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[A_ADDR_I:%.*]] = alloca i8, align 1
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca i8, align 1
// CHECK-NEXT: store i8 [[A:%.*]], ptr [[A_ADDR]], align 1
// CHECK-NEXT: [[TMP0:%.*]] = load i8, ptr [[A_ADDR]], align 1
// CHECK-NEXT: store i8 [[TMP0]], ptr [[A_ADDR_I]], align 1
// CHECK-NEXT: [[TMP1:%.*]] = load i8, ptr [[A_ADDR_I]], align 1
// CHECK-NEXT: [[CONV_I:%.*]] = zext i8 [[TMP1]] to i32
// CHECK-NEXT: [[EXTBZ_I:%.*]] = zext i8 [[TMP1]] to i32
// CHECK-NEXT: ret i32 [[EXTBZ_I]]
//
int test_alu_extbz(uint8_t a) {
return __riscv_cv_alu_extbz(a);
}
// CHECK-LABEL: @test_alu_clip(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[A_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: store i32 [[A:%.*]], ptr [[A_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK-NEXT: store i32 [[TMP0]], ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: store i32 0, ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: [[TMP3:%.*]] = call i32 @llvm.riscv.cv.alu.clip(i32 [[TMP1]], i32 [[TMP2]])
// CHECK-NEXT: ret i32 [[TMP3]]
//
int test_alu_clip(int32_t a) {
return __riscv_cv_alu_clip(a, 0);
}
// CHECK-LABEL: @test_alu_clipu(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[A_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: store i32 [[A:%.*]], ptr [[A_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK-NEXT: store i32 [[TMP0]], ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: store i32 0, ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: [[TMP3:%.*]] = call i32 @llvm.riscv.cv.alu.clipu(i32 [[TMP1]], i32 [[TMP2]])
// CHECK-NEXT: ret i32 [[TMP3]]
//
int test_alu_clipu(uint32_t a) {
return __riscv_cv_alu_clipu(a, 0);
}
// CHECK-LABEL: @test_alu_addN(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[A_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[SHFT_ADDR_I:%.*]] = alloca i8, align 1
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: store i32 [[A:%.*]], ptr [[A_ADDR]], align 4
// CHECK-NEXT: store i32 [[B:%.*]], ptr [[B_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[B_ADDR]], align 4
// CHECK-NEXT: store i32 [[TMP0]], ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: store i32 [[TMP1]], ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: store i8 0, ptr [[SHFT_ADDR_I]], align 1
// CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: [[TMP4:%.*]] = load i8, ptr [[SHFT_ADDR_I]], align 1
// CHECK-NEXT: [[CONV_I:%.*]] = zext i8 [[TMP4]] to i32
// CHECK-NEXT: [[TMP5:%.*]] = call i32 @llvm.riscv.cv.alu.addN(i32 [[TMP2]], i32 [[TMP3]], i32 [[CONV_I]])
// CHECK-NEXT: ret i32 [[TMP5]]
//
int test_alu_addN(int32_t a, int32_t b) {
return __riscv_cv_alu_addN(a, b, 0);
}
// CHECK-LABEL: @test_alu_adduN(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[A_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[SHFT_ADDR_I:%.*]] = alloca i8, align 1
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: store i32 [[A:%.*]], ptr [[A_ADDR]], align 4
// CHECK-NEXT: store i32 [[B:%.*]], ptr [[B_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[B_ADDR]], align 4
// CHECK-NEXT: store i32 [[TMP0]], ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: store i32 [[TMP1]], ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: store i8 0, ptr [[SHFT_ADDR_I]], align 1
// CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: [[TMP4:%.*]] = load i8, ptr [[SHFT_ADDR_I]], align 1
// CHECK-NEXT: [[CONV_I:%.*]] = zext i8 [[TMP4]] to i32
// CHECK-NEXT: [[TMP5:%.*]] = call i32 @llvm.riscv.cv.alu.adduN(i32 [[TMP2]], i32 [[TMP3]], i32 [[CONV_I]])
// CHECK-NEXT: ret i32 [[TMP5]]
//
int test_alu_adduN(uint32_t a, uint32_t b) {
return __riscv_cv_alu_adduN(a, b, 0);
}
// CHECK-LABEL: @test_alu_addRN(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[A_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[SHFT_ADDR_I:%.*]] = alloca i8, align 1
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: store i32 [[A:%.*]], ptr [[A_ADDR]], align 4
// CHECK-NEXT: store i32 [[B:%.*]], ptr [[B_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[B_ADDR]], align 4
// CHECK-NEXT: store i32 [[TMP0]], ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: store i32 [[TMP1]], ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: store i8 0, ptr [[SHFT_ADDR_I]], align 1
// CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: [[TMP4:%.*]] = load i8, ptr [[SHFT_ADDR_I]], align 1
// CHECK-NEXT: [[CONV_I:%.*]] = zext i8 [[TMP4]] to i32
// CHECK-NEXT: [[TMP5:%.*]] = call i32 @llvm.riscv.cv.alu.addRN(i32 [[TMP2]], i32 [[TMP3]], i32 [[CONV_I]])
// CHECK-NEXT: ret i32 [[TMP5]]
//
int test_alu_addRN(int32_t a, int32_t b) {
return __riscv_cv_alu_addRN(a, b, 0);
}
// CHECK-LABEL: @test_alu_adduRN(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[A_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[SHFT_ADDR_I:%.*]] = alloca i8, align 1
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: store i32 [[A:%.*]], ptr [[A_ADDR]], align 4
// CHECK-NEXT: store i32 [[B:%.*]], ptr [[B_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[B_ADDR]], align 4
// CHECK-NEXT: store i32 [[TMP0]], ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: store i32 [[TMP1]], ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: store i8 0, ptr [[SHFT_ADDR_I]], align 1
// CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: [[TMP4:%.*]] = load i8, ptr [[SHFT_ADDR_I]], align 1
// CHECK-NEXT: [[CONV_I:%.*]] = zext i8 [[TMP4]] to i32
// CHECK-NEXT: [[TMP5:%.*]] = call i32 @llvm.riscv.cv.alu.adduRN(i32 [[TMP2]], i32 [[TMP3]], i32 [[CONV_I]])
// CHECK-NEXT: ret i32 [[TMP5]]
//
int test_alu_adduRN(uint32_t a, uint32_t b) {
return __riscv_cv_alu_adduRN(a, b, 0);
}
// CHECK-LABEL: @test_alu_subN(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[A_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[SHFT_ADDR_I:%.*]] = alloca i8, align 1
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: store i32 [[A:%.*]], ptr [[A_ADDR]], align 4
// CHECK-NEXT: store i32 [[B:%.*]], ptr [[B_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[B_ADDR]], align 4
// CHECK-NEXT: store i32 [[TMP0]], ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: store i32 [[TMP1]], ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: store i8 0, ptr [[SHFT_ADDR_I]], align 1
// CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: [[TMP4:%.*]] = load i8, ptr [[SHFT_ADDR_I]], align 1
// CHECK-NEXT: [[CONV_I:%.*]] = zext i8 [[TMP4]] to i32
// CHECK-NEXT: [[TMP5:%.*]] = call i32 @llvm.riscv.cv.alu.subN(i32 [[TMP2]], i32 [[TMP3]], i32 [[CONV_I]])
// CHECK-NEXT: ret i32 [[TMP5]]
//
int test_alu_subN(int32_t a, int32_t b) {
return __riscv_cv_alu_subN(a, b, 0);
}
// CHECK-LABEL: @test_alu_subuN(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[A_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[SHFT_ADDR_I:%.*]] = alloca i8, align 1
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: store i32 [[A:%.*]], ptr [[A_ADDR]], align 4
// CHECK-NEXT: store i32 [[B:%.*]], ptr [[B_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[B_ADDR]], align 4
// CHECK-NEXT: store i32 [[TMP0]], ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: store i32 [[TMP1]], ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: store i8 0, ptr [[SHFT_ADDR_I]], align 1
// CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: [[TMP4:%.*]] = load i8, ptr [[SHFT_ADDR_I]], align 1
// CHECK-NEXT: [[CONV_I:%.*]] = zext i8 [[TMP4]] to i32
// CHECK-NEXT: [[TMP5:%.*]] = call i32 @llvm.riscv.cv.alu.subuN(i32 [[TMP2]], i32 [[TMP3]], i32 [[CONV_I]])
// CHECK-NEXT: ret i32 [[TMP5]]
//
int test_alu_subuN(uint32_t a, uint32_t b) {
return __riscv_cv_alu_subuN(a, b, 0);
}
// CHECK-LABEL: @test_alu_subRN(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[A_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[SHFT_ADDR_I:%.*]] = alloca i8, align 1
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: store i32 [[A:%.*]], ptr [[A_ADDR]], align 4
// CHECK-NEXT: store i32 [[B:%.*]], ptr [[B_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[B_ADDR]], align 4
// CHECK-NEXT: store i32 [[TMP0]], ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: store i32 [[TMP1]], ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: store i8 0, ptr [[SHFT_ADDR_I]], align 1
// CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: [[TMP4:%.*]] = load i8, ptr [[SHFT_ADDR_I]], align 1
// CHECK-NEXT: [[CONV_I:%.*]] = zext i8 [[TMP4]] to i32
// CHECK-NEXT: [[TMP5:%.*]] = call i32 @llvm.riscv.cv.alu.subRN(i32 [[TMP2]], i32 [[TMP3]], i32 [[CONV_I]])
// CHECK-NEXT: ret i32 [[TMP5]]
//
int test_alu_subRN(int32_t a, int32_t b) {
return __riscv_cv_alu_subRN(a, b, 0);
}
// CHECK-LABEL: @test_alu_subuRN(
// CHECK-NEXT: entry:
// CHECK-NEXT: [[A_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR_I:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[SHFT_ADDR_I:%.*]] = alloca i8, align 1
// CHECK-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: [[B_ADDR:%.*]] = alloca i32, align 4
// CHECK-NEXT: store i32 [[A:%.*]], ptr [[A_ADDR]], align 4
// CHECK-NEXT: store i32 [[B:%.*]], ptr [[B_ADDR]], align 4
// CHECK-NEXT: [[TMP0:%.*]] = load i32, ptr [[A_ADDR]], align 4
// CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr [[B_ADDR]], align 4
// CHECK-NEXT: store i32 [[TMP0]], ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: store i32 [[TMP1]], ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: store i8 0, ptr [[SHFT_ADDR_I]], align 1
// CHECK-NEXT: [[TMP2:%.*]] = load i32, ptr [[A_ADDR_I]], align 4
// CHECK-NEXT: [[TMP3:%.*]] = load i32, ptr [[B_ADDR_I]], align 4
// CHECK-NEXT: [[TMP4:%.*]] = load i8, ptr [[SHFT_ADDR_I]], align 1
// CHECK-NEXT: [[CONV_I:%.*]] = zext i8 [[TMP4]] to i32
// CHECK-NEXT: [[TMP5:%.*]] = call i32 @llvm.riscv.cv.alu.subuRN(i32 [[TMP2]], i32 [[TMP3]], i32 [[CONV_I]])
// CHECK-NEXT: ret i32 [[TMP5]]
//
int test_alu_subuRN(uint32_t a, uint32_t b) {
return __riscv_cv_alu_subuRN(a, b, 0);
}
|
